Run 3. Outer Step 9. Inner Step 98.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5410259,
-    5410263,
-    5410267,
-    5410271,
-    5410275
+    5410304,
+    5410308,
+    5410312,
+    5410316,
+    5410320
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 97,
+  "inner_step": 98,
   "inner_steps": 0,
   "last_allreduce_block": 5398844,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a02bab71904103bbb2167bcb40e1f6eb4596b7e722b8ebf36e6817af9768f74
+oid sha256:4e940a194dfae29346620b47011c05686cca663c4b0ef4d3692ce2bf8294152f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd017141eb8c33c2016025e56a451ee15ee36e73da9b5e1a8d87a3387f5d5d6b
+oid sha256:54be17d4c291885f75a8d2b4ea5b490b6e9886e72a08330383f67891194ef80b
 size 4040701744